© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 9-ATT-KK
    11. 22565
    Prev
    Next
    INDEX
    Explanations

    references to equity and respect in various social contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L9_Hcat_z_lr1.20e-03_l11.20e+00_ds24576_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v9.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    float32
    Hook Name
    blocks.9.attn.hook_z
    Hook Layer
    9
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.04
    1:0.02
    2:0.08
    3:0.10
    4:0.02
    5:0.04
    6:0.01
    7:0.04
    8:0.02
    9:0.01
    10:0.53
    11:0.02
    Negative Logits
     decipher
    -2.40
     proof
    -2.25
     proofs
    -2.20
     uncover
    -2.15
     unveil
    -2.12
     separating
    -2.10
     unlocking
    -2.07
     ascertain
    -2.05
     discover
    -2.03
     reconcile
    -2.03
    POSITIVE LOGITS
     differently
    3.63
     kindly
    3.38
     harshly
    3.21
    Kind
    2.95
    appropriately
    2.82
     unfairly
    2.79
     similarly
    2.65
     appropriately
    2.65
     correctly
    2.64
     nicely
    2.53
    Activations Density 0.152%

    No Known Activations